Casualty Actuarial Society

2018 Ratemaking, Product and Modeling (RPM) Seminar & Workshops


Workshop 1: Severe Weather

This popular workshop gives the attendees an opportunity to learn more about how Natural Catastrophe Models are developed and used within Property and Casualty Insurance. The workshop starts with a series of sessions that will explore the science underlying three Catastrophe Models (Hurricane, Flood, and Climate Change), with an opportunity for a Q&A session with representatives from Cat modeling firms. The afternoon will include sessions that explore how weather information is being used in the insurance industry, focusing in on current topics of interest.

Workshop 2: Predictive Modeling with Generalized Linear Models

*A Laptop is required for this workshop and a maximum of 40 participants will be allowed.

This popular, hands-on, interactive predictive modeling workshop has been offered at the RPM seminar now for several years. It will be conducted exclusively in the R statistical computing language, which is widely adopted by statisticians and data scientists.

The course will provide a refresher of regression theory before proceeding to a variety of practical modeling applications and case studies. The focus will be on generalized linear models (GLMs) — their specification, interpretation, and validation. A variety of distributions will be covered, including classical, Poisson, logistic, gamma, and Tweedie. Other topics will be discussed and illustrated as time permits. All datasets will be distributed to attendees prior to the seminar.

Important note: familiarity with R is assumed. An "introduction to R" presentation will be distributed before the seminar which will contain a primer on basic features and statistical functions, as well as installation instructions, that will enable beginners to get up to speed. While R beginners are encouraged to attend, they should make some attempt to become comfortable with the language prior to the workshop. This workshop has been designed for beginning predictive modelers, but more experienced modelers seeking a refresher or a deeper working knowledge of R have attended past workshops and expressed satisfaction with the coverage of topics.

Workshop 3: Product Management Workshop

This workshop will explore the different stages of the product lifecycle – from ideation through design, development, and launch – with hands-on exercises for the attendee. Industry leaders will serve as facilitators to review the various stages of the product development lifecycle and to help guide the attendees through the realities of developing an insurance product. Attendees will work in teams to develop fictitious products that will be integrated into the product development lifecycle stage discussions.

Workshop 4: Introduction to R

*A Laptop is required for this workshop and a maximum of 40 participants will be allowed.

Are you one of the millions of actuaries around the world who wish they could draw maps showing the progress of hurricanes, fit generalized linear models to predict sporting events, create complex Monte Carlo simulations, or fit loss distributions? Or maybe you’re the sort of person who wants to fit a stochastic reserving model and have a computer display stacks of pretty pictures for you. Do you want one point of access for all of your Excel, text, database and web-based data? Are you fascinated by programmers whose first names begin with the letter “R”?

If that’s the sort of person you are, this is the workshop for you. And if none of those people is you, maybe all you want is to be able to get R to work for your computer. We can take care of that too.

R is the single most important technological advance for actuaries since the invention of the pocket calculator. Come see what all the fuss is about.

Workshop 5: Basic Ratemaking

The Basic Ratemaking Workshop offers an understanding of the basic concepts and practices needed for ratemaking. These concepts include how to calculate an overall indication, how to calculate indications for various rating plans and consider data on a multivariate basis, estimating claim liabilities and large account pricing. The workshop is designed for Product Managers and Actuarial Students who have not sat for Exam 5. The sessions for the workshop will provide a basic understanding of the learning objectives that are on Exam 5.

Part 1: Fundamental Insurance Equations

This session will go over the process for developing a rate indication. Participants will gain familiarity with the steps and adjustments needed. Considerations such as loss development, trend, credibility, etc will be discussed.

Part 2: Ratemaking Relativities

This session will examine the reasons and some methods that actuaries use to allocate overall average rates to various subdivisions of a line of business. Some of the methods discussed will consist of univariate, multivariate, and generalized linear modeling techniques.

Part 3: Estimating Claim Liabilities

The session will focus on estimating claim liabilities including development factor techniques, advantages and disadvantages of different methods, and diagnostics of the various methods.

Part 4: Large Account Pricing

This session will examine the differences between large accounts and small accounts, and how they can and should be treated differently from an insurance pricing perspective. Participants will be introduced to pricing methods that both utilize the increased credibility of large account experience and recognize the uniqueness of each risk. Specifically, this session will serve as an introduction to experience rating, schedule rating, and retrospective rating.

Workshop 6: Advanced Predictive Modeling

*A laptop is required for this workshop and there will be a maximum of 40 participants.

Although the Generalized Linear Model (GLM) is a natural foundation for much actuarial work, it is best viewed as a starting point, not the last word on the subject. This day-long, hands-on workshop will discuss a variety of statistical learning methods that either refine or serve as complements to the GLM framework.

Methods for capturing potentially complex non-linear relationships, integrating credibility, tree-based modeling, and machine learning techniques will all be covered in this workshop. Core themes such as the bias-variance tradeoff and cross-validation will be woven throughout the presentation. Attendees will develop a better understanding of more advanced modeling techniques including Generalized Additive Models (GAMs), Hierarchical Models, Penalized Regression (Ridge, Lasso, Elastic Net), CART, random forests, boosting and bagging.

The workshop will assume a working knowledge of GLM modeling.

Workshop 7: Capital Allocation and Risk/Reward Decision-Making in an ERM Framework

*A laptop is required for this workshop.

This workshop will discuss aspects as developed by Merton-Perold, Myers-Read, Mango's asset share model, and the RMK procedures. Also considered will be current research as it relates to how actual capital should perhaps be considered in percentile layers and/or traunches, based on the risk metrics considered.

A laptop is needed for participation in this session as we will have hands-on technical sessions where the audience will be charged with an exercise in allocating capital to lines of business considering various methods.   Participants will work in groups to make strategic recommendations based on their respective results.  Role playing will be involved. Attendees will have access to data in advance.